Security audit
Security checks for vulnerabilities and agentic risk
This is a content-optimization helper that reads user-supplied content and produces GEO rewrite guidance, with no evidence of hidden execution, data exfiltration, persistence, or destructive behavior.
Install this as an editorial GEO helper, not as a general SEO automation tool. Only run its scripts on content files you intend to analyze, and expect the Chinese-specific playbooks and rewrite scripts to produce Chinese or mixed Chinese/English output unless the agent adapts the result for your requested language.
The skill references local scripts and bundled files and explicitly instructs the agent to read inputs from files, but it does not declare any tool scope or allowed-tools boundary. That creates an authorization ambiguity where an orchestrator may grant broader file-read capability than intended, increasing the chance of unintended access to local files during skill execution.
The description contains broad triggers like rewriting content, improving discovery, and building workflows, which can cause the skill to activate on generic editing or strategy requests outside its intended GEO scope. Over-broad activation increases the chance of inappropriate skill routing, causing the agent to apply specialized instructions or scripts in contexts where the user did not ask for them.
The skill includes a dedicated Chinese GEO mode and prescriptive Chinese-language handling without clearly requiring the user's request or content to be in Chinese. This can override user intent or cause the agent to transform content for a different language/audience than requested, which is a prompt-routing and consent problem rather than a direct code-execution issue.
This markdown file consists exclusively of Chinese-language instructions and templates, and it does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience for a documented reason. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation.
This markdown contains user-facing operational guidance exclusively in Chinese, and there is no indication that the skill is intentionally region-specific or that users may opt into another language. That can violate language or locale policy when a skill implicitly forces a specific language without user choice.
This code includes a default title string in Chinese (未命名内容) and the generated rewrite guidance is also hard-coded in Chinese or mixed Chinese/English. Because the script provides no user opt-in or configuration for language selection, it effectively forces a specific language/locale, which matches the natural-language policy violation criteria.
Multiple user-facing output fields such as top_issue_guess, rewrite_targets, suggested_sections, and quoteable_line_example are emitted in Chinese or mixed Chinese/English. Since the script does not offer a language choice or state that it is restricted to a specific locale, it imposes a language policy on all users.
This Python file hardcodes Chinese fallback strings and later emits multiple Chinese-language output strings, making the skill's behavior locale-specific by default. The file provides no option for the user to choose language and no comment indicating that the tool is intentionally limited to a Chinese-language workflow.
The generated title candidates, guidance text, comparison labels, FAQ items, and verdict are all fixed in Chinese, which forces a specific language regardless of the input file or user preference. Under the policy, locale constraints should be optional or clearly justified rather than silently imposed.
No suspicious patterns detected.
